diff --git a/sci-ml/datasets/Manifest b/sci-ml/datasets/Manifest index 75eb3044ea381..42a4d7e91381a 100644 --- a/sci-ml/datasets/Manifest +++ b/sci-ml/datasets/Manifest @@ -6,3 +6,4 @@ DIST datasets-4.4.2.gh.tar.gz 2161786 BLAKE2B 205f9bad54a01830fe4f324e5ae7f1d557 DIST datasets-4.5.0.gh.tar.gz 2165140 BLAKE2B c1a387b4a35ff5329be4ae27b8dc7208c95e2c4b51dcc47986007db7abfd98b4d974c8d60c6ef69a91e7541e8b10c2a150de939516cc8ab37f5f78865634d30a SHA512 151455b348c227f5d1a626dafcfb1e07a0d7927ebe24676e6307686946f93467848351382dc74bd0169ede5697b25798b242b69f063ba8529e5554c914bb84e7 DIST datasets-4.6.1.gh.tar.gz 2175783 BLAKE2B c8e9bcdee4befdf27c547645a7a13cdc77d57229ac6adaf312eabd77af59481ee2e60a677be3e88dcdfb2aff4943edefb4fa0fc46c6960db9d0909d78cce0a25 SHA512 a422312d6bff3cc0f382e2956bba129275300cd3c6da3ef4861dec378becd54e7ae2855390a6ef6d8b9e679fdaf739c2ef6997945097b5b28fabf03109cdcfb1 DIST datasets-4.7.0.gh.tar.gz 2185862 BLAKE2B cd1f11ddf6faf22454b20738801c58f55fb0beb6053cffc7670227a816e73d556099ad0b79c0974da6adbc8c92f30d82a41d1b870e8b97b30a12ec3135f0fa29 SHA512 2bf03d856375eea84851396dbce66fa6f2cf213efa164d4743bb242ec5cfc31b8b1b3be07a310d72926d6f81d41b133ac8225a11f1b1c67aa4a7c75169cb5311 +DIST datasets-4.8.5.gh.tar.gz 2195039 BLAKE2B 3ab237f44f852d5b6ec6b482b6f21332583ab3136991fb361ef4f64f5f23be39c38c0f6af4c1f4db43104adb1f7636a3f6fcb14f637bd73460067e3a19ebd7e4 SHA512 ceb75c23a3b695ab7bcad948b374eac7857d4e21b770b6638c47620d30cb3adc1ae4a7bafbd4076f4770ccb8782a4ff5eb1c2004cb7f6b9b54d42f7e3c169ace diff --git a/sci-ml/datasets/datasets-4.8.5.ebuild b/sci-ml/datasets/datasets-4.8.5.ebuild new file mode 100644 index 0000000000000..bfc2aa01d78b3 --- /dev/null +++ b/sci-ml/datasets/datasets-4.8.5.ebuild @@ -0,0 +1,101 @@ +# Copyright 2023-2026 Gentoo Authors +# Distributed under the terms of the GNU General Public License v2 + +EAPI=8 + +DISTUTILS_USE_PEP517=setuptools +PYTHON_COMPAT=( python3_{12..14} ) +DISTUTILS_SINGLE_IMPL=1 +inherit distutils-r1 + +DESCRIPTION="Access and share datasets for Audio, Computer Vision, and NLP tasks" +HOMEPAGE="https://pypi.org/project/datasets/" +SRC_URI="https://github.com/huggingface/${PN}/archive/refs/tags/${PV}.tar.gz + -> ${P}.gh.tar.gz" + +LICENSE="Apache-2.0" +SLOT="0" +KEYWORDS="~amd64 ~arm64" +IUSE="torch vision" +REQUIRES_USE="test? ( torch vision )" + +RDEPEND=" + sci-ml/huggingface_hub[${PYTHON_SINGLE_USEDEP}] + $(python_gen_cond_dep ' + dev-python/dill[${PYTHON_USEDEP}] + dev-python/filelock[${PYTHON_USEDEP}] + dev-python/fsspec[${PYTHON_USEDEP}] + dev-python/multiprocess[${PYTHON_USEDEP}] + dev-python/numpy[${PYTHON_USEDEP}] + dev-python/packaging[${PYTHON_USEDEP}] + dev-python/pandas[${PYTHON_USEDEP}] + dev-python/pyarrow[${PYTHON_USEDEP},parquet,snappy] + dev-python/pyyaml[${PYTHON_USEDEP}] + dev-python/requests[${PYTHON_USEDEP}] + dev-python/tqdm[${PYTHON_USEDEP}] + dev-python/xxhash[${PYTHON_USEDEP}] + vision? ( + dev-python/pillow[${PYTHON_USEDEP}] + ) + ') + torch? ( + sci-ml/caffe2[${PYTHON_SINGLE_USEDEP},numpy] + sci-ml/pytorch[${PYTHON_SINGLE_USEDEP}] + ) +" +DEPEND="${RDEPEND}" +# Missing x test: +# joblib +# joblibspark +# faiss-cpu +# jax +# jaxlib +# polars +# pyav +# pyspark +# py7zr +# s3fs +# tensorflow +# tiktoken +# torchdata +# transformers +BDEPEND="test? ( + sci-ml/torchvision[${PYTHON_SINGLE_USEDEP}] + $(python_gen_cond_dep ' + dev-python/absl-py[${PYTHON_USEDEP}] + dev-python/decorator[${PYTHON_USEDEP}] + dev-python/elasticsearch[${PYTHON_USEDEP}] + dev-python/h5py[${PYTHON_USEDEP}] + dev-python/lz4[${PYTHON_USEDEP}] + dev-python/moto[${PYTHON_USEDEP}] + dev-python/protobuf:=[${PYTHON_USEDEP}] + dev-python/pytest-datadir[${PYTHON_USEDEP}] + dev-python/pytest-xdist[${PYTHON_USEDEP}] + dev-python/soundfile[${PYTHON_USEDEP}] + dev-python/sqlalchemy[${PYTHON_USEDEP}] + dev-python/zstandard[${PYTHON_USEDEP}] + ') +)" + +EPYTEST_PLUGINS=( pytest-datadir ) + +distutils_enable_tests pytest + +python_test() { + local EPYTEST_IGNORE=( + tests/packaged_modules/test_lance.py + tests/packaged_modules/test_spark.py + ) + + local EPYTEST_DESELECT=( + tests/io/test_parquet.py::test_parquet_read_geoparquet + tests/packaged_modules/test_folder_based_builder.py::test_data_files_with_different_levels_no_metadata + tests/packaged_modules/test_folder_based_builder.py::test_data_files_with_one_label_no_metadata + tests/test_data_files.py::test_DataFilesList_from_patterns_locally_with_extra_files + tests/test_data_files.py::test_DataFilesDict_from_patterns_locally_or_remote_hashing + tests/test_hub.py::test_delete_from_hub + tests/test_load.py::test_load_dataset_builder + ) + + epytest -m 'unit' +}